English

Beyond Universal Person Re-ID Attack

Computer Vision and Pattern Recognition 2020-12-15 v3

Abstract

Deep learning-based person re-identification (Re-ID) has made great progress and achieved high performance recently. In this paper, we make the first attempt to examine the vulnerability of current person Re-ID models against a dangerous attack method, \ie, the universal adversarial perturbation (UAP) attack, which has been shown to fool classification models with a little overhead. We propose a \emph{more universal} adversarial perturbation (MUAP) method for both image-agnostic and model-insensitive person Re-ID attack. Firstly, we adopt a list-wise attack objective function to disrupt the similarity ranking list directly. Secondly, we propose a model-insensitive mechanism for cross-model attack. Extensive experiments show that the proposed attack approach achieves high attack performance and outperforms other state of the arts by large margin in cross-model scenario. The results also demonstrate the vulnerability of current Re-ID models to MUAP and further suggest the need of designing more robust Re-ID models.

Keywords

Cite

@article{arxiv.1910.14184,
  title  = {Beyond Universal Person Re-ID Attack},
  author = {Wenjie Ding and Xing Wei and Rongrong Ji and Xiaopeng Hong and Qi Tian and Yihong Gong},
  journal= {arXiv preprint arXiv:1910.14184},
  year   = {2020}
}
R2 v1 2026-06-23T12:00:13.049Z